{"title":"作为云计算标准的开放计算设备设计规范","authors":"Yahav Biran, G. Collins","doi":"10.1109/ZINC.2016.7513658","DOIUrl":null,"url":null,"abstract":"As cloud-computing becomes the primary method to run information and communication services, IT related spending toward workload processing must also increase, as it has during the last three years. A substantial portion of spending is presently dedicated to building datacenter deployments across the globe. The compute hardware equipment is at the core of the datacenters. That equipment specification is presently dictated by name-brand proprietary vendors with specific needs that encompasses the vendors offering. The data center operators are thus required to adjust their architecture to the various equipment vendors offerings to best run its service. This solution is suboptimal as specific needs might include the use of generic compute features in large scale that leave some of the system components totally unused or in low utilization limbo. We propose a model that mimics the open source software paradigm and provides a metric for technical measurement of the hardware compute system design. It uses the openCompute community as an illustrative collaboration platform. It allows a continuous improvement in the equipment specifications process based on both customer and operator needs along with evolving vendor constraints. Finally, it employs Systems Engineering theory for mitigating certain risks, and uncertainty where no meaningful data are available.","PeriodicalId":125652,"journal":{"name":"2016 Zooming Innovation in Consumer Electronics International Conference (ZINC)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Open compute-equipment design specification as a standard for cloud computing\",\"authors\":\"Yahav Biran, G. Collins\",\"doi\":\"10.1109/ZINC.2016.7513658\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As cloud-computing becomes the primary method to run information and communication services, IT related spending toward workload processing must also increase, as it has during the last three years. A substantial portion of spending is presently dedicated to building datacenter deployments across the globe. The compute hardware equipment is at the core of the datacenters. That equipment specification is presently dictated by name-brand proprietary vendors with specific needs that encompasses the vendors offering. The data center operators are thus required to adjust their architecture to the various equipment vendors offerings to best run its service. This solution is suboptimal as specific needs might include the use of generic compute features in large scale that leave some of the system components totally unused or in low utilization limbo. We propose a model that mimics the open source software paradigm and provides a metric for technical measurement of the hardware compute system design. It uses the openCompute community as an illustrative collaboration platform. It allows a continuous improvement in the equipment specifications process based on both customer and operator needs along with evolving vendor constraints. Finally, it employs Systems Engineering theory for mitigating certain risks, and uncertainty where no meaningful data are available.\",\"PeriodicalId\":125652,\"journal\":{\"name\":\"2016 Zooming Innovation in Consumer Electronics International Conference (ZINC)\",\"volume\":\"152 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 Zooming Innovation in Consumer Electronics International Conference (ZINC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ZINC.2016.7513658\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Zooming Innovation in Consumer Electronics International Conference (ZINC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ZINC.2016.7513658","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Open compute-equipment design specification as a standard for cloud computing
As cloud-computing becomes the primary method to run information and communication services, IT related spending toward workload processing must also increase, as it has during the last three years. A substantial portion of spending is presently dedicated to building datacenter deployments across the globe. The compute hardware equipment is at the core of the datacenters. That equipment specification is presently dictated by name-brand proprietary vendors with specific needs that encompasses the vendors offering. The data center operators are thus required to adjust their architecture to the various equipment vendors offerings to best run its service. This solution is suboptimal as specific needs might include the use of generic compute features in large scale that leave some of the system components totally unused or in low utilization limbo. We propose a model that mimics the open source software paradigm and provides a metric for technical measurement of the hardware compute system design. It uses the openCompute community as an illustrative collaboration platform. It allows a continuous improvement in the equipment specifications process based on both customer and operator needs along with evolving vendor constraints. Finally, it employs Systems Engineering theory for mitigating certain risks, and uncertainty where no meaningful data are available.